Archarithms’ Exigent™-DR Artificial Intelligence Computer Vision software application is built around a deep convolutional neural network architecture that exploits spatially-local correlation of features by enforcing a connectivity pattern in the synapses between neurons of adjacent layers. Coded in the Python programming language the network is trained using Archarithms’ state-of-the-art training algorithms and regularization techniques. The training techniques include Stochastic Gradient Descent, Variable Mini-batch Size, Variable Learning Rate, Dropout and Batch Normalization.
|Feature Number||Description||Unit of Measure||Price||Example|
|1||Exigent™ Automatic Target Detection software application||LS||$250,000||Drone|
|2||General Classification of Target Set||LS||$10,000||Quadcopter|
|3||Target Typing||Per Target Type||$5,000||DJI Phantom IV, DJI Mavic|
|4||Target Tracking Message||LS||$5,000||Target Highlighted In Frame|
|5||Automatic Alert||LS||$20,000||Photo of target, Type of Target, Sensor IP Address, Sensor Location|
|7||Target Orientation: Pitch, Roll, Yaw||LS||$10,000||Angles|
|8||Target Intent||LS||$50,000||Surveillance, Damage|
|9||Range||LS||$10,000||Distance From Sensor|
|10||Annual Maintenance Fee||-||15% of purchase price||-|
Electro Optical/Infrared Sensor providing a minimum of 50 pixels on target.
A computer platform with a General Purpose Graphical Processing Unit minimum 16 GB CPU RAM, 11GB GPU Memory, GPU processing speed of 1400 MHz, and GPU CUDA compute capability 6.1 or higher.
Debian flavored Linux Operating System.